If my understanding is correct, I can take one of the topics, which was used in a recent competition, and describe it. For example, in the NBME most participants gained accuracy by using NLP Pretraining techniques, so I potentially can write about it and make a submission to this competition, isn't it? Please clarify if I am wrong.
\nEDIT: Or it should be some survey on approaches, which were used during Kaggle competitions?
", "messages": [ { "id": "2256145", "postDate": "05/12/2023 09:30:43", "content": "If my understanding is correct, I can take one of the topics, which was used in a recent competition, and describe it. For example, in the NBME most participants gained accuracy by using NLP Pretraining techniques, so I potentially can write about it and make a submission to this competition, isn't it? Please clarify if I am wrong.
\nEDIT: Or it should be some survey on approaches, which were used during Kaggle competitions?
", "rawMarkdown": "If my understanding is correct, I can take one of the topics, which was used in a recent competition, and describe it. For example, in the NBME most participants gained accuracy by using NLP Pretraining techniques, so I potentially can write about it and make a submission to this competition, isn't it? Please clarify if I am wrong. \n\nEDIT: Or it should be some survey on approaches, which were used during Kaggle competitions?", "votes": null }, { "id": "2256170", "postDate": "05/12/2023 09:51:17", "content": "I think your exemple would fall within either NLP or image data because it seems to be the topic. Kaggle competitions seems to relate to the general organisation of kaggle competitions.
", "rawMarkdown": "I think your exemple would fall within either NLP or image data because it seems to be the topic. Kaggle competitions seems to relate to the general organisation of kaggle competitions.", "votes": null }, { "id": "2256187", "postDate": "05/12/2023 10:00:32", "content": "Ok. Thank you.
", "rawMarkdown": "Ok. Thank you.", "votes": null }, { "id": "2256214", "postDate": "05/12/2023 10:27:58", "content": "@lucasmorin Suppose, I would like to describe Distillation or Semi-Supervised Learning methods, which were frequently used, but I actually don't know if these topics don't belong to one of the proposed topics or even to Other (anything that does not fall into any other category).
In this analytics competition, participants will write an essay on one of the following seven topics, with a prompt to describe what the community has learned over the past 2 years of working and experimenting with:\nhas learned over the past 2 years of working and experimenting with phrase confuses me because Distillation or Semi-Supervised Learning methods are not new and they were known for the last 10+ years, so do I need to take \"2 years old \" article or method and describe it?
Maybe, it is a very very stupid question, but I would like to know these restrictions beforehand in order to not waste the next 2 months (although, it won't actually be wasted, though)
\nThanks!
", "rawMarkdown": "lucasmorin Suppose, I would like to describe Distillation or Semi-Supervised Learning methods, which were frequently used, but I actually don't know if these topics don't belong to one of the proposed topics or even to `Other (anything that does not fall into any other category)`. \n\n```\nIn this analytics competition, participants will write an essay on one of the following seven topics, with a prompt to describe what the community has learned over the past 2 years of working and experimenting with:\n```\n\n`has learned over the past 2 years of working and experimenting with` phrase confuses me because Distillation or Semi-Supervised Learning methods are not new and they were known for the last 10+ years, so do I need to take \"2 years old \" article or method and describe it? \n\nMaybe, it is a very very stupid question, but I would like to know these restrictions beforehand in order to not waste the next 2 months (although, it won't actually be wasted, though)\n\nThanks!", "votes": null }, { "id": "2256574", "postDate": "05/12/2023 15:34:46", "content": "The section \"what have we learned from the past 2 years of Kaggle competitions\" is meant to summarize the overall impact of Kaggle's competitions on the broader ML community. Did these competitions drive forward any important advancements in the field of ML? Are there any emerging techniques that started popping up in Kaggle competitions recently? Here is an old draft that had a bit more detail concerning our recommendations on how to categorize your essays:
\nIn this analytics competition, participants will write an essay on one of the following seven topics, with a prompt to describe what the community has learned over the past 2 years of working and experimenting with:
\n[1] This section (competitions) is meant to summarize the overall impact of Kaggle's competitions on the broader ML community. Did the ML community benefit from these competitions? Did these competitions drive forward any important advancements in the field of ML?
\n[2] This section (ethics) is meant to contain discussion of AI ethics as well as discussion of tools and approaches that can be used for monitoring, understanding, and mitigating risk in high-risk ML applications.
\n[3] This section (other) is meant to review anything that does not fit into any of the other categories e.g. simulations, robotics, multi-modal models, on-device ML, ML hardware, field-specific essays that discuss multiple categories, etc.
\nHopefully that helps!
", "rawMarkdown": "The section \"what have we learned from the past 2 years of Kaggle competitions\" is meant to summarize the overall impact of Kaggle's competitions on the broader ML community. Did these competitions drive forward any important advancements in the field of ML? Are there any emerging techniques that started popping up in Kaggle competitions recently? Here is an old draft that had a bit more detail concerning our recommendations on how to categorize your essays:\n\n\nIn this analytics competition, participants will write an essay on one of the following seven topics, with a prompt to describe what the community has learned over the past 2 years of working and experimenting with:\n\n - Text data\n - Image and/or video data\n - Tabular and/or time series data\n - Kaggle Competitions\n - Generative AI\n - AI ethics\n - Other (anything that does not fall into any other category)\n\n[1] This section (competitions) is meant to summarize the overall impact of Kaggle's competitions on the broader ML community. Did the ML community benefit from these competitions? Did these competitions drive forward any important advancements in the field of ML? \n\n[2] This section (ethics) is meant to contain discussion of AI ethics as well as discussion of tools and approaches that can be used for monitoring, understanding, and mitigating risk in high-risk ML applications.\n\n[3] This section (other) is meant to review anything that does not fit into any of the other categories e.g. simulations, robotics, multi-modal models, on-device ML, ML hardware, field-specific essays that discuss multiple categories, etc.\n\nHopefully that helps!", "votes": null }, { "id": "2256576", "postDate": "05/12/2023 15:36:42", "content": "You are welcome to discuss a much longer timescale (this can make a really strong introduction section I think), but we recommend focusing your essay on the most exciting recent advances.
", "rawMarkdown": "You are welcome to discuss a much longer timescale (this can make a really strong introduction section I think), but we recommend focusing your essay on the most exciting *recent* advances.", "votes": null }, { "id": "2256672", "postDate": "05/12/2023 16:40:45", "content": "Got you. Thank you!
", "rawMarkdown": "Got you. Thank you!", "votes": null } ], "comments": [ { "id": 2256170, "author_name": "lucasmorin", "author_url": "", "post_date": "05/12/2023 09:51:17", "content": "I think your exemple would fall within either NLP or image data because it seems to be the topic. Kaggle competitions seems to relate to the general organisation of kaggle competitions.
", "votes": null, "replies": [ { "id": 2256187, "author_name": "vad13irt", "author_url": "", "post_date": "05/12/2023 10:00:32", "content": "Ok. Thank you.
", "votes": null, "replies": [ { "id": 2256214, "author_name": "vad13irt", "author_url": "", "post_date": "05/12/2023 10:27:58", "content": "@lucasmorin Suppose, I would like to describe Distillation or Semi-Supervised Learning methods, which were frequently used, but I actually don't know if these topics don't belong to one of the proposed topics or even to Other (anything that does not fall into any other category).
In this analytics competition, participants will write an essay on one of the following seven topics, with a prompt to describe what the community has learned over the past 2 years of working and experimenting with:\nhas learned over the past 2 years of working and experimenting with phrase confuses me because Distillation or Semi-Supervised Learning methods are not new and they were known for the last 10+ years, so do I need to take \"2 years old \" article or method and describe it?
Maybe, it is a very very stupid question, but I would like to know these restrictions beforehand in order to not waste the next 2 months (although, it won't actually be wasted, though)
\nThanks!
", "votes": null, "replies": [ { "id": 2256576, "author_name": "paultimothymooney", "author_url": "", "post_date": "05/12/2023 15:36:42", "content": "You are welcome to discuss a much longer timescale (this can make a really strong introduction section I think), but we recommend focusing your essay on the most exciting recent advances.
", "votes": null, "replies": [] } ] } ] } ] }, { "id": 2256574, "author_name": "paultimothymooney", "author_url": "", "post_date": "05/12/2023 15:34:46", "content": "The section \"what have we learned from the past 2 years of Kaggle competitions\" is meant to summarize the overall impact of Kaggle's competitions on the broader ML community. Did these competitions drive forward any important advancements in the field of ML? Are there any emerging techniques that started popping up in Kaggle competitions recently? Here is an old draft that had a bit more detail concerning our recommendations on how to categorize your essays:
\nIn this analytics competition, participants will write an essay on one of the following seven topics, with a prompt to describe what the community has learned over the past 2 years of working and experimenting with:
\n[1] This section (competitions) is meant to summarize the overall impact of Kaggle's competitions on the broader ML community. Did the ML community benefit from these competitions? Did these competitions drive forward any important advancements in the field of ML?
\n[2] This section (ethics) is meant to contain discussion of AI ethics as well as discussion of tools and approaches that can be used for monitoring, understanding, and mitigating risk in high-risk ML applications.
\n[3] This section (other) is meant to review anything that does not fit into any of the other categories e.g. simulations, robotics, multi-modal models, on-device ML, ML hardware, field-specific essays that discuss multiple categories, etc.
\nHopefully that helps!
", "votes": null, "replies": [ { "id": 2256672, "author_name": "vad13irt", "author_url": "", "post_date": "05/12/2023 16:40:45", "content": "Got you. Thank you!
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "2256145": "If my understanding is correct, I can take one of the topics, which was used in a recent competition, and describe it. For example, in the NBME most participants gained accuracy by using NLP Pretraining techniques, so I potentially can write about it and make a submission to this competition, isn't it? Please clarify if I am wrong. \n\nEDIT: Or it should be some survey on approaches, which were used during Kaggle competitions?", "2256170": "I think your exemple would fall within either NLP or image data because it seems to be the topic. Kaggle competitions seems to relate to the general organisation of kaggle competitions.", "2256187": "Ok. Thank you.", "2256214": "lucasmorin Suppose, I would like to describe Distillation or Semi-Supervised Learning methods, which were frequently used, but I actually don't know if these topics don't belong to one of the proposed topics or even to `Other (anything that does not fall into any other category)`. \n\n```\nIn this analytics competition, participants will write an essay on one of the following seven topics, with a prompt to describe what the community has learned over the past 2 years of working and experimenting with:\n```\n\n`has learned over the past 2 years of working and experimenting with` phrase confuses me because Distillation or Semi-Supervised Learning methods are not new and they were known for the last 10+ years, so do I need to take \"2 years old \" article or method and describe it? \n\nMaybe, it is a very very stupid question, but I would like to know these restrictions beforehand in order to not waste the next 2 months (although, it won't actually be wasted, though)\n\nThanks!", "2256574": "The section \"what have we learned from the past 2 years of Kaggle competitions\" is meant to summarize the overall impact of Kaggle's competitions on the broader ML community. Did these competitions drive forward any important advancements in the field of ML? Are there any emerging techniques that started popping up in Kaggle competitions recently? Here is an old draft that had a bit more detail concerning our recommendations on how to categorize your essays:\n\n\nIn this analytics competition, participants will write an essay on one of the following seven topics, with a prompt to describe what the community has learned over the past 2 years of working and experimenting with:\n\n - Text data\n - Image and/or video data\n - Tabular and/or time series data\n - Kaggle Competitions\n - Generative AI\n - AI ethics\n - Other (anything that does not fall into any other category)\n\n[1] This section (competitions) is meant to summarize the overall impact of Kaggle's competitions on the broader ML community. Did the ML community benefit from these competitions? Did these competitions drive forward any important advancements in the field of ML? \n\n[2] This section (ethics) is meant to contain discussion of AI ethics as well as discussion of tools and approaches that can be used for monitoring, understanding, and mitigating risk in high-risk ML applications.\n\n[3] This section (other) is meant to review anything that does not fit into any of the other categories e.g. simulations, robotics, multi-modal models, on-device ML, ML hardware, field-specific essays that discuss multiple categories, etc.\n\nHopefully that helps!", "2256576": "You are welcome to discuss a much longer timescale (this can make a really strong introduction section I think), but we recommend focusing your essay on the most exciting *recent* advances.", "2256672": "Got you. Thank you!" }, "source": "meta" }